© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9335
    Prev
    Next
    INDEX
    Explanations

    words related to faith and spirituality

    oai_token-act-pair · gemini-2.0-flash

    religion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     avulla
    -0.56
     numberOfRows
    -0.50
     Gnaden
    -0.50
     vastaan
    -0.50
    OTC
    -0.48
    udesta
    -0.47
     työn
    -0.47
    حياته
    -0.46
     kanssa
    -0.46
     kysy
    -0.46
    POSITIVE LOGITS
    VersionUID
    0.57
    SPJ
    0.57
     мәкал
    0.56
    )|^{
    0.56
    ]--;
    0.56
     ognuno
    0.54
     Vikipedi
    0.54
    dieu
    0.54
    DotNetBar
    0.54
    getWriter
    0.53
    Activations Density 1.038%

    No Known Activations